system HF staff commited on
Commit
b37538f
1 Parent(s): 4350285

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +117 -0
README.md ADDED
@@ -0,0 +1,117 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language: sla
3
+ tags:
4
+ - translation
5
+
6
+ license: apache-2.0
7
+ ---
8
+
9
+ ### sla-eng
10
+
11
+ * source group: Slavic languages
12
+ * target group: English
13
+ * OPUS readme: [sla-eng](https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/sla-eng/README.md)
14
+
15
+ * model: transformer
16
+ * source language(s): bel bel_Latn bos_Latn bul bul_Latn ces csb_Latn dsb hrv hsb mkd orv_Cyrl pol rue rus slv srp_Cyrl srp_Latn ukr
17
+ * target language(s): eng
18
+ * model: transformer
19
+ * pre-processing: normalization + SentencePiece (spm32k,spm32k)
20
+ * download original weights: [opus2m-2020-08-01.zip](https://object.pouta.csc.fi/Tatoeba-MT-models/sla-eng/opus2m-2020-08-01.zip)
21
+ * test set translations: [opus2m-2020-08-01.test.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/sla-eng/opus2m-2020-08-01.test.txt)
22
+ * test set scores: [opus2m-2020-08-01.eval.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/sla-eng/opus2m-2020-08-01.eval.txt)
23
+
24
+ ## Benchmarks
25
+
26
+ | testset | BLEU | chr-F |
27
+ |-----------------------|-------|-------|
28
+ | newssyscomb2009-ceseng.ces.eng | 26.7 | 0.542 |
29
+ | newstest2009-ceseng.ces.eng | 25.2 | 0.534 |
30
+ | newstest2010-ceseng.ces.eng | 25.9 | 0.545 |
31
+ | newstest2011-ceseng.ces.eng | 26.8 | 0.544 |
32
+ | newstest2012-ceseng.ces.eng | 25.6 | 0.536 |
33
+ | newstest2012-ruseng.rus.eng | 32.5 | 0.588 |
34
+ | newstest2013-ceseng.ces.eng | 28.8 | 0.556 |
35
+ | newstest2013-ruseng.rus.eng | 26.4 | 0.532 |
36
+ | newstest2014-csen-ceseng.ces.eng | 31.4 | 0.591 |
37
+ | newstest2014-ruen-ruseng.rus.eng | 29.6 | 0.576 |
38
+ | newstest2015-encs-ceseng.ces.eng | 28.2 | 0.545 |
39
+ | newstest2015-enru-ruseng.rus.eng | 28.1 | 0.551 |
40
+ | newstest2016-encs-ceseng.ces.eng | 30.0 | 0.567 |
41
+ | newstest2016-enru-ruseng.rus.eng | 27.4 | 0.548 |
42
+ | newstest2017-encs-ceseng.ces.eng | 26.5 | 0.537 |
43
+ | newstest2017-enru-ruseng.rus.eng | 31.0 | 0.574 |
44
+ | newstest2018-encs-ceseng.ces.eng | 27.9 | 0.548 |
45
+ | newstest2018-enru-ruseng.rus.eng | 26.8 | 0.545 |
46
+ | newstest2019-ruen-ruseng.rus.eng | 29.1 | 0.562 |
47
+ | Tatoeba-test.bel-eng.bel.eng | 42.5 | 0.609 |
48
+ | Tatoeba-test.bul-eng.bul.eng | 55.4 | 0.697 |
49
+ | Tatoeba-test.ces-eng.ces.eng | 53.1 | 0.688 |
50
+ | Tatoeba-test.csb-eng.csb.eng | 23.1 | 0.446 |
51
+ | Tatoeba-test.dsb-eng.dsb.eng | 31.1 | 0.467 |
52
+ | Tatoeba-test.hbs-eng.hbs.eng | 56.1 | 0.702 |
53
+ | Tatoeba-test.hsb-eng.hsb.eng | 46.2 | 0.597 |
54
+ | Tatoeba-test.mkd-eng.mkd.eng | 54.5 | 0.680 |
55
+ | Tatoeba-test.multi.eng | 53.2 | 0.683 |
56
+ | Tatoeba-test.orv-eng.orv.eng | 12.1 | 0.292 |
57
+ | Tatoeba-test.pol-eng.pol.eng | 51.1 | 0.671 |
58
+ | Tatoeba-test.rue-eng.rue.eng | 19.6 | 0.389 |
59
+ | Tatoeba-test.rus-eng.rus.eng | 54.1 | 0.686 |
60
+ | Tatoeba-test.slv-eng.slv.eng | 43.4 | 0.610 |
61
+ | Tatoeba-test.ukr-eng.ukr.eng | 53.8 | 0.685 |
62
+
63
+
64
+ ### System Info:
65
+ - hf_name: sla-eng
66
+
67
+ - source_languages: sla
68
+
69
+ - target_languages: eng
70
+
71
+ - opus_readme_url: https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/sla-eng/README.md
72
+
73
+ - original_repo: Tatoeba-Challenge
74
+
75
+ - tags: ['translation']
76
+
77
+ - prepro: normalization + SentencePiece (spm32k,spm32k)
78
+
79
+ - url_model: https://object.pouta.csc.fi/Tatoeba-MT-models/sla-eng/opus2m-2020-08-01.zip
80
+
81
+ - url_test_set: https://object.pouta.csc.fi/Tatoeba-MT-models/sla-eng/opus2m-2020-08-01.test.txt
82
+
83
+ - src_alpha3: sla
84
+
85
+ - tgt_alpha3: eng
86
+
87
+ - short_pair: sla-en
88
+
89
+ - chrF2_score: 0.6829999999999999
90
+
91
+ - bleu: 53.2
92
+
93
+ - brevity_penalty: 0.9740000000000001
94
+
95
+ - ref_len: 70897.0
96
+
97
+ - src_name: Slavic languages
98
+
99
+ - tgt_name: English
100
+
101
+ - train_date: 2020-08-01
102
+
103
+ - src_alpha2: sla
104
+
105
+ - tgt_alpha2: en
106
+
107
+ - prefer_old: False
108
+
109
+ - long_pair: sla-eng
110
+
111
+ - helsinki_git_sha: 480fcbe0ee1bf4774bcbe6226ad9f58e63f6c535
112
+
113
+ - transformers_git_sha: 46e9f53347bbe9e989f0335f98465f30886d8173
114
+
115
+ - port_machine: brutasse
116
+
117
+ - port_time: 2020-08-18-01:48